View source on GitHub
|
Like tf.math.reduce_logsumexp.
tfp.experimental.math.softplus(
x, name='softplus'
)
This has no functional difference from the regular version, except that it's implemented inline here, allowing monkey-patching of the special functions it uses (e.g. exp).
Args | |
|---|---|
x
|
A Tensor. |
name
|
Name for the op. |
Returns | |
|---|---|
y
|
softplus(x) |